136 lines
5.3 KiB
C++
136 lines
5.3 KiB
C++
/*M///////////////////////////////////////////////////////////////////////////////////////
|
|
//
|
|
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
|
|
//
|
|
// By downloading, copying, installing or using the software you agree to this license.
|
|
// If you do not agree to this license, do not download, install,
|
|
// copy or use the software.
|
|
//
|
|
//
|
|
// License Agreement
|
|
// For Open Source Computer Vision Library
|
|
//
|
|
// Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
|
|
// Copyright (C) 2009, Willow Garage Inc., all rights reserved.
|
|
// Third party copyrights are property of their respective owners.
|
|
//
|
|
// Redistribution and use in source and binary forms, with or without modification,
|
|
// are permitted provided that the following conditions are met:
|
|
//
|
|
// * Redistribution's of source code must retain the above copyright notice,
|
|
// this list of conditions and the following disclaimer.
|
|
//
|
|
// * Redistribution's in binary form must reproduce the above copyright notice,
|
|
// this list of conditions and the following disclaimer in the documentation
|
|
// and/or other materials provided with the distribution.
|
|
//
|
|
// * The name of the copyright holders may not be used to endorse or promote products
|
|
// derived from this software without specific prior written permission.
|
|
//
|
|
// This software is provided by the copyright holders and contributors "as is" and
|
|
// any express or implied warranties, including, but not limited to, the implied
|
|
// warranties of merchantability and fitness for a particular purpose are disclaimed.
|
|
// In no event shall the Intel Corporation or contributors be liable for any direct,
|
|
// indirect, incidental, special, exemplary, or consequential damages
|
|
// (including, but not limited to, procurement of substitute goods or services;
|
|
// loss of use, data, or profits; or business interruption) however caused
|
|
// and on any theory of liability, whether in contract, strict liability,
|
|
// or tort (including negligence or otherwise) arising in any way out of
|
|
// the use of this software, even if advised of the possibility of such damage.
|
|
//
|
|
//M*/
|
|
|
|
#ifndef __UNROLL_DETAIL_HPP__
|
|
#define __UNROLL_DETAIL_HPP__
|
|
|
|
#include <thrust/tuple.h>
|
|
#include "opencv2/core/cuda/common.hpp"
|
|
#include "opencv2/core/cuda/vec_traits.hpp"
|
|
|
|
namespace detail
|
|
{
|
|
template <int cn> struct Unroll;
|
|
template <> struct Unroll<1>
|
|
{
|
|
template <int BLOCK_SIZE, typename R>
|
|
static __device__ __forceinline__ volatile R* smem_tuple(R* smem)
|
|
{
|
|
return smem;
|
|
}
|
|
|
|
template <typename R>
|
|
static __device__ __forceinline__ R& tie(R& val)
|
|
{
|
|
return val;
|
|
}
|
|
|
|
template <class Op>
|
|
static __device__ __forceinline__ const Op& op(const Op& op)
|
|
{
|
|
return op;
|
|
}
|
|
};
|
|
template <> struct Unroll<2>
|
|
{
|
|
template <int BLOCK_SIZE, typename R>
|
|
static __device__ __forceinline__ thrust::tuple<volatile R*, volatile R*> smem_tuple(R* smem)
|
|
{
|
|
return cv::gpu::cudev::smem_tuple(smem, smem + BLOCK_SIZE);
|
|
}
|
|
|
|
template <typename R>
|
|
static __device__ __forceinline__ thrust::tuple<typename cv::gpu::cudev::VecTraits<R>::elem_type&, typename cv::gpu::cudev::VecTraits<R>::elem_type&> tie(R& val)
|
|
{
|
|
return thrust::tie(val.x, val.y);
|
|
}
|
|
|
|
template <class Op>
|
|
static __device__ __forceinline__ const thrust::tuple<Op, Op> op(const Op& op)
|
|
{
|
|
return thrust::make_tuple(op, op);
|
|
}
|
|
};
|
|
template <> struct Unroll<3>
|
|
{
|
|
template <int BLOCK_SIZE, typename R>
|
|
static __device__ __forceinline__ thrust::tuple<volatile R*, volatile R*, volatile R*> smem_tuple(R* smem)
|
|
{
|
|
return cv::gpu::cudev::smem_tuple(smem, smem + BLOCK_SIZE, smem + 2 * BLOCK_SIZE);
|
|
}
|
|
|
|
template <typename R>
|
|
static __device__ __forceinline__ thrust::tuple<typename cv::gpu::cudev::VecTraits<R>::elem_type&, typename cv::gpu::cudev::VecTraits<R>::elem_type&, typename cv::gpu::cudev::VecTraits<R>::elem_type&> tie(R& val)
|
|
{
|
|
return thrust::tie(val.x, val.y, val.z);
|
|
}
|
|
|
|
template <class Op>
|
|
static __device__ __forceinline__ const thrust::tuple<Op, Op, Op> op(const Op& op)
|
|
{
|
|
return thrust::make_tuple(op, op, op);
|
|
}
|
|
};
|
|
template <> struct Unroll<4>
|
|
{
|
|
template <int BLOCK_SIZE, typename R>
|
|
static __device__ __forceinline__ thrust::tuple<volatile R*, volatile R*, volatile R*, volatile R*> smem_tuple(R* smem)
|
|
{
|
|
return cv::gpu::cudev::smem_tuple(smem, smem + BLOCK_SIZE, smem + 2 * BLOCK_SIZE, smem + 3 * BLOCK_SIZE);
|
|
}
|
|
|
|
template <typename R>
|
|
static __device__ __forceinline__ thrust::tuple<typename cv::gpu::cudev::VecTraits<R>::elem_type&, typename cv::gpu::cudev::VecTraits<R>::elem_type&, typename cv::gpu::cudev::VecTraits<R>::elem_type&, typename cv::gpu::cudev::VecTraits<R>::elem_type&> tie(R& val)
|
|
{
|
|
return thrust::tie(val.x, val.y, val.z, val.w);
|
|
}
|
|
|
|
template <class Op>
|
|
static __device__ __forceinline__ const thrust::tuple<Op, Op, Op, Op> op(const Op& op)
|
|
{
|
|
return thrust::make_tuple(op, op, op, op);
|
|
}
|
|
};
|
|
}
|
|
|
|
#endif // __UNROLL_DETAIL_HPP__
|